jinx/ComfyUI
1
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-02 23:14:49 +08:00
Code Issues Activity

Basic Genmo Mochi video model support.

Browse Source 
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.

EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
This commit is contained in:
comfyanonymous
2024-10-26 06:54:00 -04:00
parent c3ffbae067
commit 5cbb01bc2f
18 changed files with 1677 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/ldm/modules/diffusionmodules/mmdit.py
View File

@@ -97,7 +97,7 @@ class PatchEmbed(nn.Module):
self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
def forward(self, x):
B, C, H, W = x.shape
# B, C, H, W = x.shape
# if self.img_size is not None:
# if self.strict_img_size:
# _assert(H == self.img_size[0], f"Input height ({H}) doesn't match model ({self.img_size[0]}).")